首頁 > Java > java教程 > 主體

詳解Spark中將物件序列化儲存到hdfs

零下一度
發布: 2017-06-17 11:42:07
原創
2297 人瀏覽過

這篇文章主要介紹了java 中Spark中將物件序列化儲存到hdfs的相關資料,需要的朋友可以參考下

java 中Spark中將物件序列化儲存到hdfs

摘要: Spark應用程式中經常會遇到這樣一個需求: 需要將JAVA物件序列化並儲存到HDFS, 尤其是利用MLlib計算出來的一些模型, 儲存到hdfs以便模型可以重複利用. 下面的範例示範了Spark環境下從Hbase讀取資料, 產生一個word2vec模型, 儲存到hdfs.

#廢話不多說, 直接貼程式碼了. spark1.4 + hbase0.98


#
import org.apache.spark.storage.StorageLevel
import scala.collection.JavaConverters._
import java.io.File
import java.io.FileInputStream
import java.io.FileOutputStream
import java.io.ObjectInputStream
import java.io.ObjectOutputStream
import java.net.URI
import java.util.Date
import org.ansj.library.UserDefineLibrary
import org.ansj.splitWord.analysis.NlpAnalysis
import org.ansj.splitWord.analysis.ToAnalysis
import org.apache.hadoop.fs.FSDataInputStream
import org.apache.hadoop.fs.FSDataOutputStream
import org.apache.hadoop.fs.FileSystem
import org.apache.hadoop.fs.FileUtil
import org.apache.hadoop.fs.Path
import org.apache.hadoop.hbase.client._
import org.apache.hadoop.hbase.{HBaseConfiguration, HTableDescriptor, TableName}
import org.apache.hadoop.hbase.filter.FilterList
import org.apache.hadoop.hbase.filter.PageFilter
import org.apache.hadoop.hbase.filter.RegexStringComparator
import org.apache.hadoop.hbase.filter.SingleColumnValueFilter
import org.apache.hadoop.hbase.filter.CompareFilter.CompareOp
import org.apache.hadoop.hbase.mapreduce.TableInputFormat
import org.apache.hadoop.hbase.protobuf.ProtobufUtil
import org.apache.hadoop.hbase.util.{Base64, Bytes}
import com.feheadline.fespark.db.Neo4jManager
import com.feheadline.fespark.util.Env
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.rdd._
import org.apache.spark.mllib.feature.{Word2Vec, Word2VecModel}
import scala.math.log
import scala.io.Source

object Word2VecDemo {

 def convertScanToString(scan: Scan) = {
  val proto = ProtobufUtil.toScan(scan)
  Base64.encodeBytes(proto.toByteArray)
 }

 def main(args: Array[String]): Unit = {
  val sparkConf = new SparkConf().setAppName("Word2Vec Demo")
  sparkConf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
  sparkConf.set("spark.kryoserializer.buffer", "256m")
  sparkConf.set("spark.kryoserializer.buffer.max","2046m")
  sparkConf.set("spark.akka.frameSize", "500")
  sparkConf.set("spark.rpc.askTimeout", "30")
  

  val sc = new SparkContext(sparkConf)
  val hbaseConf = HBaseConfiguration.create()
  hbaseConf.set("hbase.zookeeper.quorum", "myzookeeper")

  hbaseConf.set(TableInputFormat.INPUT_TABLE, "crawled")

  val scan = new Scan()
  val filterList:FilterList = new FilterList(FilterList.Operator.MUST_PASS_ALL)
  
  val comp:RegexStringComparator = new RegexStringComparator(""".{1500,}""")
  
  val articleFilter:SingleColumnValueFilter = new SingleColumnValueFilter(
  "data".getBytes,
  "article".getBytes,
  CompareOp.EQUAL,
  comp
  )
  
  filterList.addFilter(articleFilter)
  filterList.addFilter(new PageFilter(100))
  
  scan.setFilter(filterList)
  scan.setCaching(50)
  scan.setCacheBlocks(false)
  hbaseConf.set(TableInputFormat.SCAN,convertScanToString(scan))

  val crawledRDD = sc.newAPIHadoopRDD(
   hbaseConf,
   classOf[TableInputFormat],
   classOf[org.apache.hadoop.hbase.io.ImmutableBytesWritable],
   classOf[org.apache.hadoop.hbase.client.Result]
  )
 
  val articlesRDD = crawledRDD.filter{
   case (_,result) => {
     val content = Bytes.toString(result.getValue("data".getBytes,"article".getBytes))
     content != null
   }
  }

  val wordsInDoc = articlesRDD.map{
   case (_,result) => {
     val content = Bytes.toString(result.getValue("data".getBytes,"article".getBytes))
     if(content!=null)ToAnalysis.parse(content).asScala.map(_.getName).toSeq
     else Seq("")
   }
  }
  
  val fitleredWordsInDoc = wordsInDoc.filter(_.nonEmpty)
  
  val word2vec = new Word2Vec()
  val model = word2vec.fit(fitleredWordsInDoc)
  
  //---------------------------------------重点看这里-------------------------------------------------------------
  //将上面的模型存储到hdfs
  val hadoopConf = sc.hadoopConfiguration
  hadoopConf.set("fs.defaultFS", "hdfs://myhadoop:9000/")
  val fileSystem = FileSystem.get(hadoopConf)
  val path = new Path("/user/hadoop/data/mllib/word2vec-object")
  val oos = new ObjectOutputStream(new FSDataOutputStream(fileSystem.create(path)))
  oos.writeObject(model)
  oos.close
  
  //这里示例另外一个程序直接从hdfs读取序列化对象使用模型
  val ois = new ObjectInputStream(new FSDataInputStream(fileSystem.open(path)))
  val sample_model = ois.readObject.asInstanceOf[Word2VecModel]
  
  /*
  * //你还可以将序列化文件从hdfs放到本地, scala程序使用模型
  * import java.io._
  * import org.apache.spark.mllib.feature.{Word2Vec, Word2VecModel}
  * val ois = new ObjectInputStream(new FileInputStream("/home/cherokee/tmp/word2vec-object"))
  * val sample_model = ois.readObject.asInstanceOf[Word2VecModel]
  * ois.close
  */
  //--------------------------------------------------------------------------------------------------------------
 }
}
登入後複製

以上是詳解Spark中將物件序列化儲存到hdfs的詳細內容。更多資訊請關注PHP中文網其他相關文章!

相關標籤:
來源:php.cn
本網站聲明
本文內容由網友自願投稿,版權歸原作者所有。本站不承擔相應的法律責任。如發現涉嫌抄襲或侵權的內容,請聯絡admin@php.cn
熱門教學
更多>
最新下載
更多>
網站特效
網站源碼
網站素材
前端模板
關於我們 免責聲明 Sitemap
PHP中文網:公益線上PHP培訓,幫助PHP學習者快速成長!